Repo Test Architect

Overview Schema Source Related Servers Discussions Admin

Get Plan Execution Hints

get_plan_execution_hints

Read-onlyIdempotent

Derive provider-neutral execution, context, parallel-safety, and repository-reasoning hints from a plan without invoking models or subagents.

Instructions

Derive provider-neutral execution, context, parallel-safety, and repository-reasoning hints from a plan without invoking models or subagents.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`plan`	Yes	A plan/v1 or project-test-plan/v1 artifact.
`itemId`	No	Optional stable plan item or project item id to select.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`items`	Yes
`source`	Yes
`summary`	Yes
`schemaVersion`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv1.0.0Oct 2, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$id": "https://repo-test-architect.local/schemas/plan-execution-hints-v1.schema.json",
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "additionalProperties": false,
+  "properties": {
+    "items": {
+      "items": {
+        "additionalProperties": false,
+        "properties": {
+          "action": {
+            "enum": [
+              "add-test",
+              "extend-test",
+              "defer"
+            ]
+          },
+          "adapterId": {
+            "minLength": 1,
+            "type": "string"
+          },
+          "complexity": {
+            "enum": [
+              "low",
+              "medium",
+              "high"
+            ]
+          },
+          "contextScope": {
+            "additionalProperties": false,
+            "properties": {
+              "includeBuildConfiguration": {
+                "type": "boolean"
+              },
+              "includeRepositoryInstructions": {
+                "const": true
+              },
+              "mode": {
+                "enum": [
+                  "target-only",
+                  "target-and-tests",
+                  "project-boundary"
+                ]
+              },
+              "paths": {
+                "items": {
+                  "minLength": 1,
+                  "type": "string"
+                },
+                "minItems": 1,
+                "type": "array",
+                "uniqueItems": true
+              }
+            },
+            "required": [
+              "mode",
+              "paths",
+              "includeBuildConfiguration",
+              "includeRepositoryInstructions"
+            ],
+            "type": "object"
+          },
+          "parallelizable": {
+            "type": "boolean"
+          },
+          "path": {
+            "minLength": 1,
+            "type": "string"
+          },
+          "planItemId": {
+            "minLength": 1,
+            "type": "string"
+          },
+          "projectId": {
+            "minLength": 1,
+            "type": "string"
+          },
+          "projectRoot": {
+            "minLength": 1,
+            "type": "string"
+          },
+          "reasons": {
+            "items": {
+              "minLength": 1,
+              "type": "string"
+            },
+            "minItems": 1,
+            "type": "array"
+          },
+          "recommendedAgentRole": {
+            "enum": [
+              "implementation",
+              "repository-reasoning",
+              "review"
+            ]
+          },
+          "requiresRepositoryReasoning": {
+            "type": "boolean"
+          },
+          "target": {
+            "minLength": 1,
+            "type": "string"
+          }
+        },
+        "required": [
+          "planItemId",
+          "action",
+          "target",
+          "path",
+          "complexity",
+          "contextScope",
+          "parallelizable",
+          "recommendedAgentRole",
+          "requiresRepositoryReasoning",
+          "reasons"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "schemaVersion": {
+      "const": "plan-execution-hints/v1"
+    },
+    "source": {
+      "additionalProperties": false,
+      "properties": {
+        "itemCount": {
+          "minimum": 0,
+          "type": "integer"
+        },
+        "root": {
+          "minLength": 1,
+          "type": "string"
+        },
+        "schemaVersion": {
+          "enum": [
+            "plan/v1",
+            "project-test-plan/v1"
+          ]
+        }
+      },
+      "required": [
+        "schemaVersion",
+        "itemCount"
+      ],
+      "type": "object"
+    },
+    "summary": {
+      "additionalProperties": false,
+      "properties": {
+        "highComplexityCount": {
+          "minimum": 0,
+          "type": "integer"
+        },
+        "itemCount": {
+          "minimum": 0,
+          "type": "integer"
+        },
+        "lowComplexityCount": {
+          "minimum": 0,
+          "type": "integer"
+        },
+        "mediumComplexityCount": {
+          "minimum": 0,
+          "type": "integer"
+        },
+        "parallelizableCount": {
+          "minimum": 0,
+          "type": "integer"
+        },
+        "repositoryReasoningCount": {
+          "minimum": 0,
+          "type": "integer"
+        }
+      },
+      "required": [
+        "itemCount",
+        "lowComplexityCount",
+        "mediumComplexityCount",
+        "highComplexityCount",
+        "parallelizableCount",
+        "repositoryReasoningCount"
+      ],
+      "type": "object"
+    }
+  },
+  "required": [
+    "schemaVersion",
+    "source",
+    "summary",
+    "items"
+  ],
+  "title": "Repo Test Architect Plan Execution Hints",
+  "type": "object"
+}

First observedv0.1.0Aug 4, 2026

TDQS

A3.8/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly, idempotent, and closed-world. The description adds a meaningful behavioral constraint: it runs without invoking models or subagents, which tells the agent there is no LLM cost or non-determinism involved. It still doesn't cover auth requirements or rate limits, but that's a minor gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

A single, dense sentence front-loads the verb and the output categories, then immediately adds the key constraint. No filler or redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has an output schema and full annotation coverage, so the description needn't explain return values or safety. It adequately covers input expectations and the no-model constraint. Slightly lacking in guidance on itemId or prerequisites, but still complete enough for correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with descriptions for both `plan` and `itemId`, so the schema carries the parameter semantics. The description only implies the `plan` input and adds no format, syntax, or selection details beyond what the schema provides. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb ('derive') and resource ('hints'), and scopes them to a plan and to a no-model/no-subagent computation. It does not name a sibling alternative, but it clearly differentiates itself from model-invoking tools in the same family.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies you use this when you have a plan artifact and want hints without incurring model calls, but it never states when to prefer this over siblings like generate_test_plan or explain_target, nor does it list prerequisites or exclusions. Usage is left to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.